init_pte_prot() patch
C. Jayachandran
c.jayachandran at gmail.com
Thu Jun 3 06:28:44 UTC 2010
On Thu, Jun 3, 2010 at 10:29 AM, Alan Cox <alc at imimic.com> wrote:
> I would appreciate it if someone would test the attached patch. (A
> "buildworld" would probably suffice.) Essentially, it does two things:
>
> 1. The virtual memory system only cares about the contents of a page's dirty
> field if that page is managed (i.e., it is pageable). And, in fact, if you
> survey the calls to vm_page_dirty() in the MIPS or any other pmap, they are
> generally conditioned on the mapping having been for a managed page.
>
> The MIPS pmap_enter() is an exception to this rule. It is unconditionally
> calling vm_page_dirty() on any page mapped within the kernel address space,
> managed or otherwise. In fact, it is highly unusual for pmap_enter() to be
> calling vm_page_dirty() on the page being mapped, regardless of whether it
> is managed. This call to vm_page_dirty() shouldn't be needed if change #2
> below is also made. The attached patch eliminates the call.
>
> 2. Since the virtual memory system only cares about the contents of a page's
> dirty field if that page is managed, then dirty bit emulation need only be
> performed on managed pages. At present, init_pte_prot() skips emulation if
> the address being mapped is in the kernel. However, this is not really the
> right condition to test for. There do exist some managed pages in the
> kernel address space, and it is also possible through System V shared memory
> to have unmanaged pages in the user address space. The attached patch bases
> the emulation decision on whether the page is managed.
I have added this patch to my buildworld test (make -j128 buildworld
on a 8-core MIPS SoC) and it seems to be holding up. It will take a
few hours to run over NFS - will update if I get anything.
JC.
More information about the freebsd-mips
mailing list